Statistical tests based on geodesic distances

Abstract Burbea and Rao [1] gave some general methods for constructing quadratic differential metrics on probability spaces. Using these methods, they obtain the Fisher information metric as a particular case. In this paper, a procedure to test statistical hypotheses is proposed on the basis of geodesic distances. An example is given and the asymptotic distribution of the test statistics are obtained; so, this method can be used in those cases where it is not possible to get the exact distribution of the test statistics.